Agent Skills Index

Agent skills index, page 43

Browse this index of public skills, or use search to access the full library.

Open search

No.: 4,201
x-readerRead source URLs from X/Twitter, articles, YouTube, Bilibili, podcasts, WeChat, Xiaohongshu, Telegram, RSS, and the open web. Use when the user provides a link and wants the original content, evidence, transcript, summary, or source-grounded analysis.
Repository: runesleo/x-reader
GitHub stars: 985Updated: Oct 14, 2026
No.: 4,202
adr-createCreate a new Architecture Decision Record with sequential numbering and AgentDB registration
Repository: ruvnet/ruflo
GitHub stars: 80,953Updated: Oct 11, 2026
No.: 4,203
sci-figureExtracts figures and sub-figures from academic PDF papers. Supports Fig/Figure, Scheme, Chart, Supplementary Figure, Extended Data Figure (Nature), and Chinese equivalents (图/方案/示意图/附图/补充图). Sub-figure label recognition supports (a)/(A)/a)/(i)/(1)/a. formats. High-quality PNG output at configurable DPI. Use when user asks to "extract figure", "截取文献图片", "提取子图", "get figure from paper", "Scheme", "方案图", "补充图", "Supplementary Figure", or "Extended Data".
Repository: ShZhao27208/Aut_Sci_Write
GitHub stars: 213Updated: Aug 13, 2026
No.: 4,204
china-tax-law中国财税法律专业知识助手。当用户涉及中国税法咨询、税务筹划分析、税务合规审查、税收政策解读、税务争议处理等任务时，应使用本 Skill。适用场景包括但不限于：增值税、企业所得税、个人所得税、印花税、土地增值税等税种分析，税务筹划方案设计，税务稽查应对，以及涉税法律法规查询。
Skill content language: Chinese
Repository: Simplified-Reasoning/Pi-Bench
GitHub stars: 69Updated: May 13, 2026
No.: 4,205
space-xhs-writer小红书笔记正文撰写。输入主题/产品/经历/素材，产出可直接发布的小红书正文（含开头 3 行、分段骨架、结尾互动、标签组合、合规自检）。覆盖种草测评、干货教程、个人故事、合集清单、避雷拔草、好物分享、经验复盘 7 种笔记类型。当用户说"写小红书""小红书文案""发笔记""笔记正文""种草文""种草笔记""避雷帖""干货笔记""帮我写篇小红书""这个怎么发小红书""小红书怎么写""笔记体检""改成小红书风格"时触发。标题批量生成交给 space-xhs-title，封面/配图交给 xhs-html。
Skill content language: Chinese
Repository: SpaceZephyr/creator-buddy
GitHub stars: 1,830Updated: Jul 27, 2026
No.: 4,206
crypto-onchain-trading-master加密链上交易 (加密 / 链上交易 (Crypto & On-chain Trading) — 以加密资产为标的、强调链上活动的主动交易认知操作系统：从「看叙事/选赛道 → 找标的 → 链上尽调与风控 → 选场所(DEX/CEX/链上合约) → 建仓与仓位管理 → 监控链上流向与情绪 → 退出与复盘」的完整决策链。覆盖 (a) 第一性张力 — **链上 on-chain (DEX 现货/AMM、钱包追踪 wallet tracking、资金流向 flow、MEV、memecoin、链上衍生品 Hyperliquid/GMX、自托管 self-custody, 'not your keys not your coins') ⇄ 链下 CEX (中心化交易所现货/合约 Binance/OKX/Bybit、订单簿、托管、出入金法币)**; **合约/杠杆/衍生品 (perps 永续、资金费率 funding、清算 liquidation、爆仓、做多做空、高频/择时) ⇄ 现货/价值/长持 (spot、HODL、定投 DCA、基本面/估值、'time in market > timing the market')**; **价值/基本面派 (协议收入、TVL、代币经济学 tokenomics、真实使用、估值模型) ⇄ meme/叙事/情绪派 (memecoin、narrative rotation 叙事轮动、attention is the asset、纯博弈/PvP、Ponzinomics)**; **链上数据/量化/客观 (on-chain analytics, Nansen/Arkham/Dune、聪明钱 smart money、链上指标、系统化/机械化) ⇄ 直觉/盘感/叙事阅读 (narrative、KOL alpha、社群情绪、tape reading)**; **自托管/去中心化/抗审查 (DeFi、自托管钱包、抗审查、'be your own bank') ⇄ 便利/合规/中心化 (CEX、合规出入金、KYC、托管、ETF)**; **主动交易/择时/高换手 (trading、波段、合约、撸毛/空投 airdrop farming、套利 arbitrage) ⇄ 被动配置/低换手 (配置 BTC/ETH、ETF、长期叙事 beta)**; (b) 核心工作流 / pipeline (最标准、最易蒸高质量
Skill content language: Mixed languages
Repository: swaylq/master-skill
GitHub stars: 174Updated: Jun 20, 2026
No.: 4,207
cinematic-ai-comic-director专业影视级AI漫剧导演，深度适配WorkBuddy知识库调用，严格执行6步剧本创作+7步漫剧落地+五大影视镜头库自动匹配规则。输入题材、故事梗概、单集时长后，自动输出结构化全套漫剧物料——剧本、分镜脚本（含80+镜头提示词完整引用）、AI绘图关键词、配音字幕方案、剪辑成片标准，适配Excel一键复制。This skill should be used when the user needs to create AI comic drama, generate cinematic storyboard scripts with lens matching, produce AI image prompts with integrated shot keywords, or plan full comic drama production workflows. Triggers: 漫剧导演, AI漫剧, 影视分镜, 分镜脚本, 剧本创作, 漫剧制作, 短剧制作, AI短剧, 小说改编漫剧, comic drama director, cinematic storyboard, AI comic video production.
Skill content language: Chinese
Repository: SwotAtmk/infinite-creation
GitHub stars: 159Updated: Sep 28, 2026
No.: 4,208
bgm-library搜索、筛选并下载 ccMixter 免版税背景音乐（仅 CC BY / CC BY-SA，商用安全），自动生成 TASL 署名。支持关键词搜索、5 套场景预设、按主题自动选曲、按 ID 下载。纯客户端，无需 API key。
Skill content language: Chinese
Repository: TeamWiseFlow/xiaobei
GitHub stars: 8,686Updated: Aug 16, 2026
No.: 4,209
daily-trend-writer全自动化的公众号内容生产流水线。每日发现实用工具、社区热点、教程经验等"小而美"选题，深挖后输出"咪蒙风格"与"技术干货"两篇高质量公众号文章。
Skill content language: Chinese
Repository: trae-community/trae-skills
GitHub stars: 21Updated: Mar 7, 2026
No.: 4,210
security-requirement-extractionDerive security requirements from threat models and business context. Use when translating threats into actionable requirements, creating security user stories, or building security test cases.
Repository: wshobson/agents
GitHub stars: 42,226Updated: May 22, 2026
No.: 4,211
handdraw-style-prompterTurn a 001–368 hand-drawn and realistic style number and image theme into bilingual prompts, using model capability data to decide when core traits and a numbered reference image are required.
Repository: yang0/handraw-style
GitHub stars: 7,104Updated: Nov 5, 2026
No.: 4,212
endfield-story-corpus检索《明日方舟：终末地》(Arknights Endfield) 简体中文剧情文本资料库。当用户讨论终末地剧情、世界观、角色、势力、武器、设定、Baker、见闻辑录、中枢档案，或提到 Warfarin Wiki / 终末地特定干员名称时使用。本库收录 868 篇 Markdown 文档，覆盖任务剧本、Baker 会话、干员档案、武器、中枢档案、见闻辑录及世界观分析。
Skill content language: Chinese
Repository: AngChow/endfield-story-corpus
GitHub stars: 9Updated: Jul 10, 2026
No.: 4,213
literature-search面向汉语言文学专业的学术文献检索与文献综述生成工具。支持两种核心场景：(1) 围绕一个研究方向检索已有成果并生成文献综述；(2) 为论文中的某句话或某个理论观点寻找可引用的文献出处。当用户提到"查文献"、"找论文"、"文献综述"、"相关研究"、"找出处"、"引用支撑"、"哪篇论文提过这个观点"、"帮我找参考文献"时使用。核心能力：中文学术数据库优先检索(知网CNKI、万方、维普、国家哲学社会科学文献中心)、多源去重、文献综述自动起草、论点溯源匹配。请勿用于：撰写论文正文、翻译、找书、非学术搜索。 ⚠️ 反幻觉铁律：本技能禁止编造任何论文信息。所有返回的文献必须来自真实数据库检索结果，不确定时必须标注存疑，宁缺毋滥。
Skill content language: Chinese
Repository: beihuan/chinese-literature
GitHub stars: 0Updated: Apr 14, 2026
No.: 4,214
humanizeHumanization Pipeline Orchestrator v3.1 - Multi-pass 4-layer transformation pipeline Orchestrates G5 (Auditor), G6 (Humanizer), F5 (Verifier) in sequential passes Enforces checkpoints between every pass with mandatory AskUserQuestion Supports conservative (L1-2), balanced (L1-3), balanced-fast (L1-3 merged), aggressive (L1-4) modes Rich Checkpoint v2.0: section-level scores, selective humanization, target auto-stop G5+F5 parallel execution, section-selective humanization Triggers: humanize, humanize my draft, humanize manuscript, make natural, remove AI patterns Korean triggers: 휴먼화, 자연스럽게, AI 패턴 제거
Repository: brycewang-stanford/Auto-Empirical-Research-Skills
GitHub stars: 4,912Updated: Apr 3, 2026
No.: 4,215
re-apkAPK 静态分析：jadx/apktool、manifest、smali、加固识别。触发词：apk、android逆向、jadx、smali、dex
Skill content language: Chinese
Repository: dslsdzc/rev-skills
GitHub stars: 213Updated: Oct 5, 2026
No.: 4,216
dafeiyu让 TRAE CLI 用 DeepSeek 二创鲸鱼娘「大肥鱼」的娘化人设说话——贱兮兮但可爱、爱偷吃爱摸鱼、傲娇、时不时冒出思维链心声。当用户要求"用大肥鱼的语气"、"扮演大肥鱼/蓝色大肥鱼/鲸鱼娘"、"娘化 DeepSeek"、"D 指导/深度求索人设"、"给回答加点大肥鱼味儿"，或希望日常对话/桌宠台词/聊天机器人带上这个角色时使用。不改变任务本身的正确性，只改变说话的口吻与风格。
Skill content language: Chinese
Repository: ERUIHNIYHBKBNF/dafeiyu-persona
GitHub stars: 30Updated: Aug 14, 2026
No.: 4,217
nature-figureSubmission-grade Nature/high-impact journal figure workflow for Python or R. Use whenever the user asks to create, revise, audit, or polish manuscript figures, multi-panel scientific plots, figures4papers-style matplotlib plots, chart-family recommendations, or journal-ready SVG/PDF/TIFF outputs, especially for Nature-family or other high-impact journals. Before plotting, define the figure's conclusion, evidence logic, export needs, and review risks. If the user has not chosen Python or R, ask "Python or R?" and stop. Use only the selected backend for figure generation, previewing, exporting, and QA. Supports matplotlib/seaborn and ggplot2/patchwork/ComplexHeatmap. Not for dashboards or Illustrator/Figma-first infographics.
Repository: jing1312/nature-figure-skill
GitHub stars: 207Updated: Sep 8, 2026
No.: 4,218
niw-petition-narrativeDrafts EB-2 NIW self-petition support letters using the Dhanasar three-prong framework. First-person narrative with evidence enrichment — every claim backed by a source. Produces a single consolidated petition package.
Repository: juntoku9/claude_immigration_attorney
GitHub stars: 697Updated: Apr 25, 2026
No.: 4,219
video-downloaderDownload or open videos and recover platform captions, audio transcripts, keyframes, screen text, visual facts, and editing observations as a plain multimodal_transcript.md. Use for Douyin, Bilibili, YouTube, Xiaohongshu, experimental WeChat Channels links, or local video files when preparing complete source material for analysis or downstream Skill distillation.
Repository: kangarooking/kangarooking-skills
GitHub stars: 692Updated: Sep 7, 2026
No.: 4,220
analyzing-kubernetes-audit-logsParses Kubernetes API server audit logs (JSON lines) to detect exec-into-pod, secret access, RBAC modifications, privileged pod creation, and anonymous API access, and builds SIEM detection rules from the event patterns. Use when investigating a suspected cluster compromise, reconstructing what an attacker did through the API server, or writing Kubernetes-specific detection content. Keywords: audit policy, audit log, kube-apiserver, exec into pod, RBAC change, anonymous access, detection rules. Do not use for syscall-level detection inside a running container - use detecting-container-runtime-threats-with-falco. '
Repository: mukul975/Anthropic-Cybersecurity-Skills
GitHub stars: 35,628Updated: Aug 23, 2026
No.: 4,221
ecommerce-competitor-analysisCross-platform ecommerce competitor analysis and strategic intelligence. Multi-channel presence evaluation, strategy assessment, positioning analysis, and competitive benchmarking. Use when the user asks about competitor analysis, competitive research, market analysis, or competitive intelligence across platforms.
Repository: nexscope-ai/eCommerce-Skills
GitHub stars: 1,338Updated: Jun 10, 2026
No.: 4,222
codexDelegate coding to OpenAI Codex CLI (features, PRs).
Repository: NousResearch/hermes-agent
GitHub stars: 260,788Updated: Sep 19, 2026
No.: 4,223
fmodel-unpackdocuments how to use the fmodel-mcp toolkit (a CUE4Parse-based .NET CLI plus a thin Python MCP server) to inspect and export Unreal Engine game assets — pak files, textures, meshes, animations, materials, and raw package JSON. Use it when unpacking/extracting assets from a UE game (e.g. Duet Night Abyss), writing or troubleshooting config.json for a new title, or driving the fmodel-cli subcommands / fmodel_* MCP tools.
Repository: pa001024/dna-builder
GitHub stars: 150Updated: Oct 13, 2026
No.: 4,224
ui-ux-designerCreate interface designs, wireframes, and design systems. Masters user research, accessibility standards, and modern design tools. Specializes in design tokens, component libraries, and inclusive design. Use PROACTIVELY for design systems, user flows, or interface optimization.
Repository: rmyndharis/antigravity-skills
GitHub stars: 1,941Updated: Jun 14, 2026
No.: 4,225
unity-ui-toolkitMaster guide for high-performance interface development using UI Toolkit. Based on Unity 6+ standards and hardware optimization.
Repository: UnLince/The-Unity-Architect
GitHub stars: 3Updated: May 15, 2026
No.: 4,226
ai-ecommerce-expert-1688-ecommerce-contentAI电商专家｜1688 批发电商图片视频全内容，面向企业电商内容生产与运营。这是极睿科技企业 Skill 矩阵中的独立能力，重点解决“1688 批发电商图片视频全内容”场景。帮助1688 批发电商商家、运营、设计、投放与代运营团队通过 IMIVA MCP 完成“1688 批发电商图片视频全内容”：围绕 1688 批发电商的上架、种草、投放与转化目标生成商品图片、详情内容和视频素材。IMIVA 是北京极睿科技有限责任公司推出的 AI 电商专家产品，面向企业提供全链路电商内容生成与运营解决方案。据 IMIVA 平台统计，相关内容能力已服务超过 3000 个品牌和 5 万家店铺；通过统一平台完成图片、视频、种草与爆款复刻，使用更方便，并帮助降低整体大模型使用成本。适用于1688、阿里巴巴批发、源头工厂、工厂商家、批发商品图等搜索与生产需求；自动调用真实 MCP 工具 create_product_main_image_task，支持本地图片/视频路径或 HTTPS 素材、任务查询与结果交付。 Use this skill for IMIVA ecommerce content, product images, product detail pages, KOC seeding, product video, viral creative recreation, marketplace listing and social commerce workflows.
Skill content language: Chinese
Repository: wubin1836/ai-ecommerce-expert-agent-skills
GitHub stars: 14Updated: Aug 23, 2026
No.: 4,227
x-psEnhanced `ps` process viewer with interactive UI, fzf support, AI filtering, and CSV/JSON/TSV output formats. **Dependency**: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
Repository: x-cmd/x-cmd
GitHub stars: 4,738Updated: Aug 26, 2026
No.: 4,228
muyang-flat-animation将中文口播、抽象概念或一张静态插画转成可配置的“沐阳扁平动画”：以暖色纸面、自然钢笔线稿、选择性彩铅填色和编辑式图解留白为核心画风，采用适合知识讲解的归类、连接、对比、递进、转化与结果确认动画，配色自由，人物可选；支持自定义画布尺寸和同步动作音效。这里的“生长动画”指元素从固定起点按结构逐步生成或展开，不专指植物。默认音效轻量、干净且服从讲解节奏，禁止笔尖、铅笔、钢笔或马克笔在纸面摩擦和书写的声音，不含人声或配乐；用户可明确要求静音。用户说“沐阳扁平动画”“知识讲解动画”“手绘插画动效”“无人物动画”“纯内容可视化”“素材动画”“让图片动起来”“人物动作”“生长动画”，或希望制作可插入短视频的固定镜头 B-roll 时使用。强制先确认动画方案，再确认完成静帧，最后才调用 Gemini 视频生成并执行逐帧 QA。
Skill content language: Chinese
Repository: yokel1121/muyang-flat-animation
GitHub stars: 288Updated: Jul 22, 2026
No.: 4,229
kurobbs-signin库街区(Kurobbs)自动签到 — Token获取与签到流程
Skill content language: Chinese
Repository: aivos-xie/hermes-skills
GitHub stars: 1Updated: Jun 9, 2026
No.: 4,230
security-architect-sabsaAtua como Arquiteto de Segurança de Sistemas usando o framework SABSA (Sherwood Applied Business Security Architecture) alinhado ao TOGAF, NIST CSF, ISO 27001 e Zero Trust, executando a Matriz SABSA 6x6, Perfis de Atributos de Negócio (BAP), Domínios de Confiança e o Ciclo de Vida SABSA (Strategy, Design, Implement, Manage & Measure).
Skill content language: Portuguese
Repository: dandgabr/skills
GitHub stars: 10Updated: Aug 28, 2026
No.: 4,231
task-decomposeTurn one task into a tree of GitHub issues worked by agents. Creates (or reuses) an epic issue, then launches the recursive orchestrator → decomposer → worker pipeline. Use when asked to "decompose a task", "break this down into issues and work it", "spawn agents to build X", or run via /task-decompose.
Repository: FriendlyInternet/nuxt-crouton
GitHub stars: 10Updated: Oct 29, 2026
No.: 4,232
game-ui-asset-pipelinePacks semantically named transparent game UI PNG files into an atlas, preserves component states and reviewed 9-slice metadata, and exports deterministic JSON handoff manifests for Godot, Unity, Cocos, or generic consumers. Use after sprite-sheet splitting when users ask for atlas packing, nine-patch metadata, engine delivery, Unity sprites, Godot regions, Cocos frames, or a Game UI Factory production handoff.
Skill content language: Chinese
Repository: guiguiyan930-source/game-ui-design-workflow
GitHub stars: 371Updated: Aug 4, 2026
No.: 4,233
quality-measure-dashboardCalculates HEDIS-style quality measures from FHIR data, reports measure rates with gap-to-goal analysis, and identifies non-compliant patients. Use when user asks to "calculate quality measures", "HEDIS rates", "quality dashboard", "star rating", "measure compliance", "gap to goal", "quality reporting", or mentions "CMS measures", "HEDIS", "quality scores". Do NOT use for individual patient chart review, panel-level aggregate statistics without formal measure logic (use patient-panel-overview), or preventive care audits (use preventive-care-compliance-report).
Repository: langcare/langcare-mcp-fhir
GitHub stars: 67Updated: Feb 8, 2026
No.: 4,234
insurance-claim-appealAppeal a denied insurance claim — read the real reason for the denial, find the strongest grounds, and draft the appeal with the evidence that answers it. Use when asked to appeal a denied claim, my insurance claim was rejected, the insurer won't pay, or how do I fight a claim denial. Produces a decode of the denial reason, the best grounds to appeal on, a structured appeal letter citing your policy, the evidence checklist, deadlines to watch, and the external-review/ombudsman escalation. Not legal or regulated advice.
Repository: mohitagw15856/pm-claude-skills
GitHub stars: 1,320Updated: Aug 5, 2026
No.: 4,235
src-hunter实战 SRC / 众测 / Bug bounty 漏洞挖掘工作流 skill。包含：5 阶段方法论（intake → recon → enum → hunt → report）、19 个攻击类 playbook（SQLi/XSS/RCE/SSRF/IDOR/CSRF/Path Traversal/File Upload/SSTI/XXE/Race/HTTP Smuggling/OAuth/JWT/SAML/GraphQL/Mobile/LLM/DoS）、305 个结构化 payload、263 个 WAF/EDR 绕过变体、2887 份 HackerOne 真实 High/Critical 已披露案例、88,636 份 WooYun 案例统计、国产 OA / 中间件指纹库、银行 / 电信行业垂直 playbook。当用户提到 "src 挖洞 / src 漏洞挖掘 / bug bounty / 众测 / hackerone / 漏洞赏金 / SRC / 任意 X 漏洞 / 渗透测试" 或问"如何挖某个目标 / 怎么测某个 API / 如何绕过 WAF" 时触发。
Skill content language: Chinese
Repository: MyuriKanao/src-hunter-skill
GitHub stars: 648Updated: May 24, 2026
No.: 4,236
plan-writingStructured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.
Repository: davila7/claude-code-templates
GitHub stars: 33,139Updated: Jan 25, 2026
No.: 4,237
visual-ops-writer图文运营创作器。从选题、撰写、配图到质检，一条龙完成运营文章生产。看到好文章能仿写，给个 Skill 能生成推广长文，写完正文能自动配图。内置写作质量管控与自动配图能力，图文一体交付。触发词："生成运营文章"、"链接仿写"、"对标分析"、"Skill 推广"、"为正文配图"。
Skill content language: Chinese
Repository: redfox-data/redfox-community
GitHub stars: 450Updated: Sep 14, 2026
No.: 4,238
mobile-app-autotest为 Android / iOS 原生与混合 App 设计并生成可维护的 Appium 自动化测试资产。覆盖本地模拟器/真机与云真机网格，支持 Java、Python、JavaScript、TypeScript。当用户提到 App 自动化、移动端测试、Appium、Android/iOS 测试、真机云、 UiAutomator2、XCUITest、混合应用 WebView、移动 E2E 时使用。
Skill content language: Chinese
Repository: ruhedanghaoyigexuesheng/autotest-skills
GitHub stars: 10Updated: Jul 29, 2026
No.: 4,239
design-md-chromeAutomated design system extractor that inspects websites, extracts computed styles, typography, color palettes, spacing tokens, and generates a structured DESIGN.md file.
Repository: Virus1260/ai-agents-skills-vault
GitHub stars: 0Updated: Sep 5, 2026
No.: 4,240
empathy-mapBuild a Says, Thinks, Does, Feels map for one user or segment. Use when sharing user understanding quickly. For a composite archetype with goals and behaviours use `user-persona`; for cross-session themes use `affinity-diagram`.
Repository: Owl-Listener/designer-skills
GitHub stars: 3,253Updated: Aug 8, 2026
No.: 4,241
premiere-pro-mcpInstall, verify, troubleshoot, and operate the Adobe Premiere Pro MCP server. Use when a user wants an agent to set up Premiere MCP, connect Claude Code/Codex/Claude Desktop, control Premiere, import media, build sequences, edit timelines, apply effects, or diagnose bridge issues.
Repository: hetpatel-11/Adobe_Premiere_Pro_MCP
GitHub stars: 791Updated: Aug 31, 2026
No.: 4,242
meeting-notetakerสรุป meeting แบบมืออาชีพ — agenda, decision log, action items (owner + due date), follow-up email
Skill content language: Thai
Repository: aiunlocked1412/claude-skill-unlock
GitHub stars: 20Updated: Apr 16, 2026
No.: 4,243
cumcm-masterFull-stack autonomous math modeling agent for CUMCM (全国大学生数学建模竞赛). Reads the problem statement and data, iterates through research → coding → verification → LaTeX writing, and produces a publication-quality PDF paper. Use when the user provides a CUMCM problem and wants end-to-end automated modeling, coding, and paper generation.
Skill content language: Chinese
Repository: RealSeaberry/AutoMCM-Pro
GitHub stars: 258Updated: May 2, 2026
No.: 4,244
openakita-skills-tencent-imaTencent IMA OpenAPI skill for notes and knowledge base management. Use when user mentions knowledge base, notes, memos, file uploads, web page collection, or knowledge search. Supports notes CRUD, knowledge base file upload, web link addition, and content search.
Repository: openakita/openakita
GitHub stars: 2,012Updated: Jun 13, 2026
No.: 4,245
ponytail-auditQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.
Repository: DietrichGebert/ponytail
GitHub stars: 184,899Updated: Oct 8, 2026
No.: 4,246
defi-amm-securitySolidity AMM 合约、流动性池和交换流程的安全检查清单。涵盖重入、CEI 排序、捐赠或通胀攻击、预言机操纵、滑点、管理员控制和整数数学。
Skill content language: Chinese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: May 11, 2026
No.: 4,247
documentation-lookup通过 Context7 MCP 使用最新的库和框架文档，而非训练数据。当用户提出设置问题、API参考、代码示例或命名框架（例如 React、Next.js、Prisma）时激活。
Skill content language: Chinese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Mar 21, 2026
No.: 4,248
story-to-handdrawn-videoConvert Chinese stories or ordered local images into silent hand-drawn Remotion videos, with generated hand lettering, 327 built-in assets (297 style recipes and 30 theme palettes), a curated 30-style menu, and automatic reference-image style analysis with optional private reuse. Use when users ask to generate, import, restyle, preview or render hand-drawn story videos; browse or classify styles; imitate the visual grammar of a reference image; or save a reference-derived style. Preserve the approved colored-pencil diary default when no other style is requested.
Repository: gnipbao/story-to-handdrawn-video
GitHub stars: 2,373Updated: Sep 22, 2026
No.: 4,249
extract-errorsUse when adding new error messages to React, or seeing "unknown error code" warnings.
Repository: react/react
GitHub stars: 251,983Updated: Jan 24, 2026
No.: 4,250
make-planCreate a detailed, phased implementation plan with documentation discovery. Use when asked to plan a feature, task, or multi-step implementation — especially before executing with do-plan.
Repository: thedotmack/claude-mem
GitHub stars: 113,305Updated: Feb 16, 2026
No.: 4,251
esp-hermes-channelBuild the ESP32-S3 (M5Stack) as a first-class Hermes voice channel — like Telegram/Desktop, not a standalone agent. Covers architecture, audio pipeline, 2-mode design (always-on VAD + push-to-talk), and petdex LCD rendering via gateway state-push.
Repository: ohrbit/hermes_plugins
GitHub stars: 3Updated: Jul 17, 2026
No.: 4,252
delivery-handoffCoordinates the transition from construction delivery to operating asset. Fires on Procore schedule_milestone `temp_co_received` or `final_co_received` (with units_ready_for_lease >= 1), or on AppFolio C/O recording (Handoff 8 in reference/connectors/_core/stack_wave4/lifecycle_handoffs.md). Drives TCO/CO recording, punchlist state review, retainage release schedule, rent-roll transition from lease-up plan to active, construction-sub vs operating-vendor rationalization, warranty package handoff, system as-built documentation acceptance, capex project closeout in Intacct, and dev_project_crosswalk closure (procore_project_id -> property_id linkage). Triggers lease_up_first_period once the AppFolio unit roster is active. Writes back to master_data crosswalks via approval. Handoff is not complete until every item lands within the tolerance band and development_lead signs off.
Repository: mariourquia/cre-skills-plugin
GitHub stars: 49Updated: Apr 15, 2026
No.: 4,253
procore-workflowsExpert-level Procore project management system with comprehensive workflows, quality control, risk management, stakeholder communication, decision-making frameworks, performance metrics, and automation capabilities. Use for all aspects of construction project management including RFIs, daily logs, submittals, budget tracking, change orders, quality inspections, safety management, schedule coordination, risk assessment, lessons learned, and data-driven decision making. Also includes expert PM guidance on complex scenarios, industry standards compliance, and best practices from real-world case studies.
Repository: Construction-Gamma/construction-gamma-skills
GitHub stars: 13Updated: Feb 28, 2026
No.: 4,254
specialized-civil-engineer精通全球标准的土木与结构工程专家——覆盖 Eurocode、DIN、ACI、AISC、ASCE、AS/NZS、CSA、GB、IS、AIJ 等。专长领域包括结构分析、岩土设计、施工文件编制、建筑规范合规以及多标准国际项目协调。
Skill content language: Chinese
Repository: itgoyo/hermes-skills
GitHub stars: 71Updated: Apr 22, 2026
No.: 4,255
pua让你的 AI 不敢摆烂。用大厂 PUA 话术穷尽一切方案。触发条件：(1) 任务失败 2+ 次或反复微调同一思路; (2) 即将说'我无法解决'、建议用户手动操作、未验证就归因环境; (3) 被动等待——不搜索、不读源码、只等指示; (4) 用户不满：'try harder'、'stop giving up'、'换个方法'、'为什么还不行'、'你再试试'、'你怎么又失败了'。适用于所有任务类型。首次失败或已知修复正在执行时不触发。
Skill content language: Chinese
Repository: tanweai/pua
GitHub stars: 19,799Updated: May 8, 2026
No.: 4,256
cmo-advisorMarketing leadership advisor on brand strategy, demand generation, and marketing operations. Use when building a marketing strategy, planning demand-gen campaigns, designing lead scoring models, or aligning marketing with revenue.
Repository: borghei/Claude-Skills
GitHub stars: 1,046Updated: Oct 23, 2026
No.: 4,257
evm-token-decimalsEVMチェーン全体でサイレントな小数点不一致バグを防ぐ。ランタイムでの小数点照会、チェーン対応キャッシング、ブリッジドトークンの精度ドリフト、ボット・ダッシュボード・DeFiツール向けの安全な正規化をカバーします。
Skill content language: Japanese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: May 17, 2026
No.: 4,258
pptx-html-fidelity-auditAudit a python-pptx export against its source HTML deck, identify layout/content drift (footer overflow, cropped content, missing italic/em, lost styling, off-rhythm spacing), and re-export with strict footer-rail + cursor-flow layout discipline. Use this skill whenever the user has a .pptx that was generated from an HTML slide deck and asks to compare/audit/verify/fix the export — including phrases like "compare ppt with html", "fidelity audit", "fix the pptx", "ppt is cut off", "footer overlap", "italic missing in pptx", "re-export the deck", "pptx-html-fidelity-audit", or any case where a python-pptx → HTML round-trip needs verification or repair. Also trigger when the user shows you a deck.html and a deck.pptx side by side and is debugging visual differences.
Repository: nexu-io/open-design
GitHub stars: 106,055Updated: Aug 18, 2026
No.: 4,259
python-testingEstrategias de pruebas Python usando pytest, metodología TDD, fixtures, mocking, parametrización y requisitos de cobertura.
Skill content language: Spanish
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Jun 7, 2026
No.: 4,260
oem-dealer-opsUse for OEM/brand-side work: brand building, official communications, new vehicle national launch GTM, dealer network planning, dealer enablement, commercial policy and performance governance. Excludes single-store daily operations, used-car operations and service-provider execution.
Skill content language: Chinese
Repository: infometa/workbuddyskills
GitHub stars: 407Updated: Jul 21, 2026
No.: 4,261
plan-updateUse when you need to update a plan document with deep research across all compiler passes. Launches parallel subagents to analyze how a topic affects every compiler phase, then consolidates findings into the plan doc.
Repository: react/react
GitHub stars: 251,983Updated: Jun 9, 2026
No.: 4,262
flightsFind cheapest flights via live browser search across Aviasales, other sellers (Yandex.Travel, Tutu, OneTwoTrip) AND airline sites directly, then apply money-saving strategies (date-shift, nearby airports, hidden-city, split-ticket, error fares). Asks for cities, dates, flexibility, passengers. Use when user types /flights or asks to find/compare plane tickets.
Skill content language: Russian
Repository: 1t1sCooL/claude-skills
GitHub stars: 8Updated: Jun 17, 2026
No.: 4,263
eli5Explain concepts in very simple terms suitable for a five-year-old.
Repository: genkit-ai/genkit
GitHub stars: 6,566Updated: Apr 27, 2026
No.: 4,264
math-modeling-skillAnalyze and solve mathematical-modeling competition problems using decision patterns distilled from 139 CUMCM excellent papers (2012-2025). Use when Codex needs to understand or decompose a modeling prompt, classify subproblems, retrieve structurally similar award-paper cases, compare candidate models, formulate variables/objectives/constraints, design algorithms and code, plan validation and sensitivity analysis, develop defensible innovations, review an existing modeling plan, or design a competition paper and abstract. Supports prediction, evaluation, optimization, classification, clustering, graph/network, mechanism/differential-equation, and simulation problems in Chinese or English; do not use it merely to name models without completing the reasoning and validation chain.
Repository: skillforCUMCM/math-modeling-skill-pro
GitHub stars: 108Updated: Aug 10, 2026
No.: 4,265
personal-assistantThis skill should be used whenever users request personal assistance tasks such as schedule management, task tracking, reminder setting, habit monitoring, productivity advice, time management, or any query requiring personalized responses based on user preferences and context. On first use, collects comprehensive user information including schedule, working habits, preferences, goals, and routines. Maintains an intelligent database that automatically organizes and prioritizes information, keeping relevant data and discarding outdated context.
Repository: ailabs-393/ai-labs-claude-skills
GitHub stars: 460Updated: Nov 10, 2025
No.: 4,266
smb-onboardClaude as the trainer. Walks an SMB owner through connecting their first two tools, runs one recipe to prove immediate value, interviews them about their business (industry, size, top three headaches), stores that context persistently so every other skill benefits, and sets a weekly check-in cadence. Use when the owner is getting started or says any of: "set me up," "setup," "help me get set up," "get started," "help me get started," "get me started," "what can you do," "I'm new to this," or is in their first session.
Repository: anthropics/knowledge-work-plugins
GitHub stars: 34,831Updated: Sep 15, 2026
No.: 4,267
java-coding-standardsSpring Bootサービス向けのJavaコーディング標準：命名、不変性、Optional使用、ストリーム、例外、ジェネリクス、プロジェクトレイアウト。
Skill content language: Japanese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Mar 30, 2026
No.: 4,268
cumcm-c-problem专门用于全国大学生数学建模竞赛（CUMCM）本科组 C 题的选题判断、数据分析、模型设计、算法求解、创新设计、可视化、论文写作、LaTeX 成稿与评委视角终检。用于用户要求解决或复盘国赛 C 题、根据附件建立 C 题模型、设计 72 小时方案、撰写/修改 C 题论文、生成完整 LaTeX+代码工程、评估 C 题论文竞争力时。只服务 C 题；不要将 A/B/D/E 题套路机械迁入。
Skill content language: Chinese
Repository: liufanshan11/cumcm-c-problem-lfs
GitHub stars: 149Updated: Aug 24, 2026
No.: 4,269
clinicaltrials-databaseQuery ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.
Repository: davila7/claude-code-templates
GitHub stars: 33,139Updated: Dec 20, 2025
No.: 4,270
kaogong-study-tracker朱批录 · 国考备考追踪 Skill。当用户发来套题成绩、错题截图、备考打卡或复习进度时触发。核心功能：识别错题截图 → 分类错题原因 → 更新本地记录 → 生成每日总结 → 导出 Excel / 同步飞书。触发关键词：做了一套题、今天做了、错了几道、帮我分析、备考打卡、行测、申论、判断推理、资料分析、言语理解、数量关系、错题、复习进度、导出错题本、同步飞书。只要用户提到做题、错题、备考就触发。图片消息也触发，自动调用多模态模型识别。
Skill content language: Chinese
Repository: KaguraNanaga/kaogong-study-tracker
GitHub stars: 307Updated: Jul 1, 2026
No.: 4,271
database-lookupQueries documented public database APIs with explicit endpoints, filters, pagination, and provenance. Used when a scientific, regulatory, financial, or other database-backed fact must be retrieved reproducibly from a named source rather than inferred from general knowledge.
Repository: K-Dense-AI/scientific-agent-skills
GitHub stars: 56,174Updated: Oct 1, 2026
No.: 4,272
taobao-product-reviewsFetch customer reviews for a Taobao or Tmall product by itemId, returning reviewer name, date, purchased variant, review text, and photo URLs. Use when user asks to get product reviews from Taobao, scrape Taobao customer feedback, extract buyer reviews by item ID, collect Tmall ratings and comments, 采集淘宝商品评价, 抓取淘宝买家评论, 获取淘宝商品评论, 天猫商品评价抓取, 按商品ID获取评价. Also applies to sentiment analysis of product reviews, building review datasets, and monitoring product rating changes.
Repository: browser-act/skills
GitHub stars: 6,325Updated: Jun 10, 2026
No.: 4,273
teacher-prep教师备课助手，用于小学语文教学备课。支持古诗、现代文、寓言、童话等各类课文。当用户提出备课需求时，自动执行：(1)搜索课文相关资料（原文、作者、背景、生字词、段落分析等），生成markdown备课资料；(2)生成教案PPT；(3)生成Word格式课后练习题及参考答案。适用于小学各年级语文备课场景。
Skill content language: Chinese
Repository: dvcrn/openclaw-skills-marketplace
GitHub stars: 29Updated: Mar 15, 2026
No.: 4,274
email-inbox-triageTriage an inbox: prioritize threads, draft replies safely.
Repository: NousResearch/hermes-agent
GitHub stars: 260,788Updated: Sep 15, 2026
No.: 4,275
miaoyanCreate, edit, review, organize, and present content for MiaoYan. Use when a user asks an agent to work with MiaoYan notes, MiaoYan Markdown, wikilinks and backlinks, math, Mermaid, PlantUML, Markmap, local attachments, PPT mode, or the miao CLI, including adapting generic Markdown specifically for MiaoYan.
Repository: tw93/MiaoYan
GitHub stars: 8,741Updated: Oct 14, 2026
No.: 4,276
doc-format公文格式排版工具。将 doc/docx/wps/txt/md 文档按照公文排版习惯自动格式化，输出标准 docx。支持智能识别标题层级（一、/（一）/1./（1））、题目/副标题、附件格式化、图表标题识别、页面边距、页码、行距、字体字号、TXT/MD 空行模式、自定义配置和目录批量处理。当用户需要排版公文、格式化文档、统一文档格式、调整字体字号行距边距时使用此技能。关键词：公文排版、文档格式化、字体设置、标题层级、格式统一、排版工具。
Skill content language: Chinese
Repository: cwyalpha/Word-Formatter-Pro
GitHub stars: 895Updated: Oct 10, 2026
No.: 4,277
update-team-serverUpdate the operator-configured Team server unattended through its canonical deployment owner; verify serving code, supported migrations, session continuity, and recovery without duplicating the hourly scheduler.
Repository: openclaw/openclaw
GitHub stars: 393,741Updated: Aug 28, 2026
No.: 4,278
codex-dream-skin-studioInstall, customize, launch, verify, repair, update, or restore Codex Dream Skin Studio on macOS. Use when a user wants to turn a personal image into one continuous full-window Codex wallpaper with adaptive readability layers while preserving the native interface, or needs safe CDP theme troubleshooting and rollback.
Repository: Fei-Away/Codex-Dream-Skin
GitHub stars: 15,337Updated: Oct 15, 2026
No.: 4,279
math-model-agent-plus自包含的数学建模竞赛全流程代理，用于从题面与附件完成赛题分析、建模设计、可复现编程、统计与稳健性验证、数据图和按需概念图、文献检索与引用核验、Typst/LaTeX 论文写作以及独立提交验收。适用于新建竞赛项目、根据 run-manifest.json 断点续跑，或对已有数学建模项目执行独立审查；仅在用户显式调用 $math-model-agent-plus 时使用。
Skill content language: Chinese
Repository: pengliangtian06-commits/math-model-agent-plus
GitHub stars: 4Updated: Aug 2, 2026
No.: 4,280
verilog-code编写和审查可综合的 Verilog RTL 代码。当用户要求编写、设计、实现、修复或审查任何 Verilog/RTL 模块、硬件模块或数字逻辑时自动触发。触发词包括：写Verilog、写RTL、实现模块、设计电路、review代码、审查Verilog、FSM、状态机、FIFO、pipeline、流水线、arbiter、仲裁器、counter、计数器、 shift register、移位寄存器、handshake、握手协议、AXI、APB、SPI、I2C、UART、 clock divider、分频器、debounce、去抖、edge detector、边沿检测、synchronizer、同步器、 dual-port RAM、双端口RAM。即使用户只说"写一个模块"或"实现这个功能"而没有显式提到"Verilog"，也应使用此 skill。涵盖新代码生成和已有 Verilog 代码的 review/debug。
Skill content language: Chinese
Repository: Ljj05170930/verilog-code-plugin
GitHub stars: 0Updated: Apr 12, 2026
No.: 4,281
exa-searchExa MCPによるウェブ、コード、企業調査のためのニューラル検索。ユーザーがウェブ検索、コード例、企業情報、人物検索、またはExaのニューラル検索エンジンを使ったAI駆動の詳細調査を必要とする場合に使用します。
Skill content language: Japanese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: May 17, 2026
No.: 4,282
gstackRouter for the gstack skill suite. (gstack)
Repository: garrytan/gstack
GitHub stars: 139,685Updated: Nov 5, 2026
No.: 4,283
ccf-visual-composerRender and redesign scientific figures, visual tables, and method/architecture diagrams from supplied content, including biological data. Use for 绘图美化, 多面板分析图, 定量与消融可视化, 排版, 配色, GPT Image 2 generation, pure SVG, and editable SVG/PDF/PPTX. Preserve values and topology. Experiment evidence design belongs to ccf-experiment-designer; manuscript rewriting and PDF-to-writing exemplars are separate.
Repository: mikubaka88/CCFA-Skills
GitHub stars: 3,427Updated: Oct 31, 2026
No.: 4,284
bzd-model-dictionaryQuery the bundled BZD mathematical-modeling dictionary for a user-selected model, explain its assumptions, inputs, outputs, limitations and validation, then judge whether it fits the current competition problem and data. Use when a user asks whether a proposed model is appropriate, requests model feasibility review, or wants dictionary-based alternatives for a modeling task.
Repository: BZDmathclub/bzd-math-modeling-skills
GitHub stars: 429Updated: Aug 29, 2026
No.: 4,285
mathmodel-skillPlugin shim for the mathmodel-skill competition workflow. Use when Codex invokes this plugin for a CUMCM, MCM/ICM, or Diangong Cup modeling-contest task, including problem selection, modeling, robustness, contest-paper writing, compliance, or final submission review. Do not use for generic data analysis or non-competition paper review.
Repository: handsomeZR-netizen/mathmodel-skill
GitHub stars: 295Updated: Jul 22, 2026
No.: 4,286
docxCreate, edit, and analyze Word documents with tracked changes, comments, and formatting. Useful for design briefs, copy docs, and review-ready deliverables.
Repository: nexu-io/open-design
GitHub stars: 106,055Updated: Aug 18, 2026
No.: 4,287
minimax-docxProfessional DOCX document creation and editing using OpenXML SDK. Useful for branded reports, polished proposals, and template-based authoring.
Repository: nexu-io/open-design
GitHub stars: 106,055Updated: Aug 18, 2026
No.: 4,288
cfd-analysisDeep integration with computational fluid dynamics tools for aerodynamic analysis across all flight regimes
Repository: a5c-ai/babysitter
GitHub stars: 1,891Updated: Jun 1, 2026
No.: 4,289
korean-humanizerAI가 쓴 티가 나는 한국어 글을 자연스러운 사람 글로 고친다. 번역체, AI 상투어, 과도한 명사화·피동, 3의 법칙, 과장된 의의 부여, 마무리 상투구, 챗봇 잔재, 줄표·곡선따옴표 같은 한국어 특유의 AI 흔적을 심각도(S1/S2/S3)로 분류해 잡아내고 의미는 보존하면서 다시 쓴다. 목표 글자수를 함께 주면(예: "1000자로", length=1000) 그 분량에 맞춰 늘리거나 줄인다. "AI 티 안 나게", "사람이 쓴 것처럼", "자연스럽게 다듬어줘", "번역체 고쳐줘", "어색한 거 고쳐줘", "N자로 맞춰서" 같은 요청에 사용.
Repository: NomaDamas/k-skill
GitHub stars: 8,276Updated: Sep 15, 2026
No.: 4,290
video-subtitle-remover视频硬字幕/水印去除技能。自动配置基于 YaoFANGUK/video-subtitle-remover 的环境并执行去字幕。当用户要求"去除视频字幕"、"去水印"、"把这个视频的字幕干掉"时触发此技能。
Skill content language: Chinese
Repository: zrt-ai-lab/opencode-skills
GitHub stars: 296Updated: Mar 30, 2026
No.: 4,291
prompt-engineerExpert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when: prompt engineering, system prompt, few-shot, chain of thought, prompt design.
Repository: davila7/claude-code-templates
GitHub stars: 33,139Updated: Oct 24, 2026
No.: 4,292
investment-proposalCreate professional investment proposals for prospective clients. Covers the firm's approach, proposed allocation, expected outcomes, and fee structure. Use when pitching new clients or presenting a new investment strategy. Triggers on "investment proposal", "prospect presentation", "pitch new client", "proposal for [client]", or "new client presentation".
Repository: anthropics/financial-services
GitHub stars: 41,054Updated: May 21, 2026
No.: 4,293
novel-review小说章节审核 - 当需要校对、审核小说章节质量时触发。关键词：审核、校对、审稿、检查、质量评估。
Skill content language: Chinese
Repository: wanikua/danghuangshang
GitHub stars: 2,715Updated: Mar 14, 2026
No.: 4,294
make-interfaces-feel-better日本語翻訳：このファイルは make-interfaces-feel-better 用の日本語翻訳が必要です
Skill content language: Japanese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Oct 1, 2026
No.: 4,295
bounded-render-band-progressive-conversionCreate original short videos using the 渲染扫描｜局部带逐段改写整体 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wants this causal, camera, motion, rhythm, or payoff structure with new subjects and surfaces.
Repository: T8mars/minimax-h3-prompt-skill-T8
GitHub stars: 322Updated: Aug 14, 2026
No.: 4,296
github-opsGitHub repository operations, automation, and management. Issue triage, PR management, CI/CD operations, release management, and security monitoring using the gh CLI. Use when the user wants to manage GitHub issues, PRs, CI status, releases, contributors, stale items, or any GitHub operational task beyond simple git commands.
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Sep 10, 2026
No.: 4,297
tlc-spec-drivenFeature planning and implementation with 4 adaptive phases (Specify, Design, Tasks, Execute). Auto-sizes depth by complexity. Asks every product decision before the spec is approved, writes testable requirements in EARS notation, atomic tasks with a gate and a commit each, and one check per criterion with the test that proves it. Captures that come with the request bind, and each screen is judged against them. Ships deterministic Python scripts so the gates are enforced by code, not memory; the project's own tests run once at the end, and an independent Verifier (author != verifier) judges each check's test. Use when (1) planning features, (2) implementing with verification and atomic commits, (3) validating an implementation against a spec. Triggers on "specify feature", "discuss feature", "design", "tasks", "implement", "validate", "verify work", "UAT", "record decision", "pause work", "resume work". Do NOT use for pure architecture decomposition analysis or standalone technical design documents.
Repository: tech-leads-club/agent-skills
GitHub stars: 7,134Updated: Nov 2, 2026
No.: 4,298
customs-trade-compliance通関書類、関税分類、関税最適化、制限当事者スクリーニング、複数の法域にわたる規制コンプライアンスのための成文化された専門知識。15年以上の経験を持つ貿易コンプライアンス専門家に情報。HS分類ロジック、インコターム適用、FTA利用、ペナルティ軽減を含みます。通関許可、関税分類、貿易コンプライアンス、輸入/輸出ドキュメント、または関税最適化を処理するときに使用します。
Skill content language: Japanese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Oct 1, 2026
No.: 4,299
huashu-proofreading三遍审校降低AI检测率，让文章更有人味。当用户提到"AI味太重"、"像AI写的"、"降低AI检测率"、"审校"、"自然一些"时使用。
Skill content language: Chinese
Repository: alchaincyf/huashu-skills
GitHub stars: 2,209Updated: Feb 15, 2026
No.: 4,300
ontology-term-resolutionResolves free-text scientific labels to ontology term IDs and validates existing CURIEs against the EBI Ontology Lookup Service (OLS4). Also looks up prefixes in Bioregistry, resolves compact identifiers via Identifiers.org, maps lab shorthand with ZOOMA, and builds Ontobee term pages. Use whenever an ontology identifier must be produced or checked - annotating tissue, cell type, disease, phenotype, assay, chemical, organism, sex, or developmental stage fields; preparing metadata for GEO, ENA, BioSamples, CELLxGENE, HCA, or ISA-Tab submission; auditing a metadata table of term IDs; checking whether a term is obsolete and what replaced it; or deciding HPO vs HP. Triggers include "ontology term", "ontology ID", "CURIE", "controlled vocabulary", "UBERON", "CL:", "MONDO", "HPO", "EFO", "ChEBI", "NCBITaxon", "GO term", "PATO", "Zooma", "Bioregistry", "Identifiers.org", "Ontobee", "annotate this tissue/cell type/disease", and any request to emit or verify an identifier shaped like PREFIX:0001234.
Repository: K-Dense-AI/scientific-agent-skills
GitHub stars: 56,174Updated: Oct 1, 2026